{ "run_name": "clinical-agent-transformer-mcp-full", "dataset_path": "/root/generated_data/amr_mcp_traces_balanced_v1.jsonl", "dataset_records": 1800, "train_records": 1620, "validation_records": 180, "text_field": "text_trace", "resume_trainable_state": "/checkpoints/runs/clinical-agent-transformer-clinical-full/trainable_state.pt", "seq_len": 1024, "train_steps": 1200, "gradient_accumulation_steps": 8, "learning_rate": 2e-05, "warmup_steps": 100, "eval_every": 100, "checkpoint_every": 0, "losses": [ 8.261292934417725, 8.163441836833954, 8.177353203296661, 8.168348789215088, 8.076540052890778, 7.815936863422394, 7.896245896816254, 7.62277615070343, 7.4410223960876465, 7.2093111872673035, 6.975111722946167, 6.913655698299408, 6.826074838638306, 6.770330011844635, 6.720040142536163, 6.698519468307495, 6.608599305152893, 6.593647480010986, 6.469860732555389, 6.429429352283478, 6.311609864234924, 6.294034957885742, 6.333190381526947, 6.2032288908958435, 6.074349761009216, 6.041495740413666, 6.140882134437561, 5.9048484563827515, 5.890208125114441, 5.841541886329651, 5.716970205307007, 5.772250652313232, 5.625128269195557, 5.614135146141052, 5.610735833644867, 5.650689780712128, 5.3798434138298035, 5.436018347740173, 5.404404997825623, 5.440618932247162, 5.351420223712921, 5.34623920917511, 5.2838539481163025, 5.104320526123047, 5.148950219154358, 5.184379279613495, 5.016061782836914, 5.0828863978385925, 5.025748550891876, 4.951754093170166, 4.833639204502106, 4.771369397640228, 4.717774152755737, 4.820539176464081, 4.857066333293915, 4.711103618144989, 4.688219845294952, 4.597307562828064, 4.551635921001434, 4.58421665430069, 4.543719947338104, 4.522010385990143, 4.627478539943695, 4.5739825963974, 4.445137023925781, 4.332988440990448, 4.372862100601196, 4.223928719758987, 4.305863559246063, 4.347627282142639, 4.413300424814224, 4.344864457845688, 4.242972820997238, 4.031886100769043, 4.015578389167786, 4.046565592288971, 4.039056867361069, 3.900683283805847, 4.09597909450531, 3.9002828896045685, 3.835624784231186, 3.958367168903351, 3.8370602130889893, 3.79279163479805, 3.9009659588336945, 3.707729309797287, 3.931636482477188, 3.6938535571098328, 3.8825665414333344, 3.7894521355628967, 3.691390246152878, 3.6710696518421173, 3.6318428814411163, 3.5484158098697662, 3.615939825773239, 3.608551263809204, 3.575754702091217, 3.3789921402931213, 3.6145372688770294, 3.357224851846695, 3.2021254301071167, 3.317003160715103, 3.2356558740139008, 3.2960659563541412, 3.3148950040340424, 3.4104406535625458, 3.1494440734386444, 3.035324215888977, 3.2058411836624146, 3.1177440881729126, 3.0983194708824158, 3.0439885556697845, 3.15883806347847, 3.017989546060562, 3.022290915250778, 2.783576160669327, 2.9367659389972687, 3.0676648914813995, 2.87437841296196, 2.7975026667118073, 2.908842533826828, 2.7392400205135345, 2.744791567325592, 2.844683438539505, 2.839159846305847, 2.68056720495224, 2.7747884690761566, 2.796884149312973, 2.7488940060138702, 2.635950803756714, 2.6342001259326935, 2.6462216675281525, 2.461296558380127, 2.521627187728882, 2.602918356657028, 2.590325504541397, 2.382751762866974, 2.4930808544158936, 2.722613275051117, 2.3861756324768066, 2.371595025062561, 2.273716986179352, 2.5188612043857574, 2.454538345336914, 2.192589610815048, 2.29652301967144, 2.218859925866127, 2.4165745079517365, 2.1988307386636734, 2.379779040813446, 2.2218600660562515, 2.351611077785492, 2.089180052280426, 2.047184944152832, 2.2281170338392258, 2.2691055089235306, 2.2565267384052277, 2.252262979745865, 2.127178728580475, 2.1124915182590485, 2.1496333926916122, 2.1908611059188843, 2.0274095833301544, 2.1065411269664764, 2.0067661851644516, 2.2191324532032013, 2.16944819688797, 1.9189021289348602, 1.9401672929525375, 2.1057000309228897, 2.0840209424495697, 1.7573165744543076, 2.039648413658142, 1.9279413521289825, 1.9530391693115234, 2.029738172888756, 1.852142572402954, 2.0695592015981674, 1.8634213209152222, 1.8441505432128906, 1.8793940097093582, 1.7200284749269485, 1.7787855565547943, 1.9997882544994354, 1.8214413076639175, 1.6856354027986526, 1.773601919412613, 1.873384416103363, 1.7972178608179092, 1.7428040653467178, 1.675266981124878, 1.792445808649063, 1.6473048031330109, 1.6831112056970596, 1.8643322885036469, 1.83014278113842, 1.582194447517395, 1.6508467942476273, 1.9354162812232971, 1.5165023356676102, 1.7517023533582687, 1.6173395961523056, 1.5287262946367264, 1.7858741879463196, 1.4788846671581268, 1.5867124646902084, 1.5561960190534592, 1.6554233729839325, 1.5400921255350113, 1.491695910692215, 1.4784211963415146, 1.5193863958120346, 1.5498751401901245, 1.5506616234779358, 1.5459262281656265, 1.474884569644928, 1.5531335920095444, 1.5825363099575043, 1.6134756356477737, 1.6596762537956238, 1.6337790042161942, 1.7885078191757202, 1.563613697886467, 1.524568423628807, 1.5064586102962494, 1.5275050550699234, 1.426622360944748, 1.6496621668338776, 1.4984694570302963, 1.352784439921379, 1.4005490243434906, 1.5127532333135605, 1.3917295038700104, 1.3841590583324432, 1.4242000728845596, 1.341633826494217, 1.3221472650766373, 1.3372543305158615, 1.5550192445516586, 1.3542469441890717, 1.3506201952695847, 1.3569926247000694, 1.2599622830748558, 1.4619792848825455, 1.414371706545353, 1.3867833316326141, 1.336819350719452, 1.4502881616353989, 1.5559400767087936, 1.3817663490772247, 1.3430901169776917, 1.3946528285741806, 1.3066276833415031, 1.410971961915493, 1.485862135887146, 1.3613857999444008, 1.270927645266056, 1.1764065474271774, 1.3578307330608368, 1.286030799150467, 1.2731995061039925, 1.2166038751602173, 1.3690613955259323, 1.4206503480672836, 1.344714730978012, 1.256966508924961, 1.1711866557598114, 1.2315493300557137, 1.3222937881946564, 1.2547919899225235, 1.2769374176859856, 1.243523545563221, 1.2905475348234177, 1.3598639592528343, 1.2796455845236778, 1.3255695179104805, 1.217159129679203, 1.3680592253804207, 1.2360766157507896, 1.319083996117115, 1.106729917228222, 1.0924593657255173, 1.221852533519268, 1.3107096701860428, 1.3262690901756287, 1.299238458275795, 1.2409028112888336, 1.0797364488244057, 1.05547846108675, 1.2110453397035599, 1.2175423502922058, 1.0959933996200562, 1.2728222087025642, 1.1497194170951843, 1.2054239436984062, 1.1784898713231087, 1.109102837741375, 1.2680979073047638, 1.1282253861427307, 1.3894686102867126, 1.181386113166809, 1.2538943216204643, 1.1525194719433784, 1.0266179740428925, 1.1835416406393051, 0.9641729444265366, 1.0768364071846008, 1.1317846700549126, 1.19680754840374, 1.0605319067835808, 1.127291738986969, 1.2485387846827507, 1.3692906498908997, 1.153185285627842, 1.0923219919204712, 1.198511391878128, 1.1153592839837074, 1.194333016872406, 1.1558924615383148, 1.0611468479037285, 0.9382420927286148, 1.1343865022063255, 1.286887101829052, 1.204506516456604, 1.0209220349788666, 1.1177350282669067, 1.1662729308009148, 1.254777431488037, 0.974289134144783, 1.1003568172454834, 0.9976173117756844, 1.072183333337307, 1.037683680653572, 0.9447217956185341, 1.1154351383447647, 0.9924660697579384, 0.9295914247632027, 1.1033475324511528, 0.9178490713238716, 1.0206055045127869, 1.0365506559610367, 1.0742135643959045, 1.153308667242527, 1.1000603586435318, 1.181698277592659, 1.178374096751213, 0.9976721554994583, 0.9967296347022057, 1.0217666998505592, 1.0837212279438972, 0.9211557507514954, 0.8493126183748245, 1.052629142999649, 1.0446335077285767, 1.1020954921841621, 0.950236864387989, 1.0292977914214134, 0.9989157915115356, 0.9790527895092964, 0.9801187738776207, 0.9753928929567337, 0.9387145861983299, 0.9429062828421593, 0.8961929082870483, 0.9168933555483818, 0.9345762357115746, 0.9300728514790535, 1.108024537563324, 1.0151402354240417, 1.023547574877739, 1.0121103078126907, 1.0898807495832443, 0.9832864478230476, 0.905247151851654, 0.971100702881813, 0.9229184538125992, 0.9642638638615608, 1.0275908187031746, 0.8781033530831337, 0.8919804319739342, 1.1377196609973907, 1.0486371219158173, 0.8669855296611786, 0.9467231631278992, 1.102805957198143, 0.9239240661263466, 0.82939163595438, 0.8827033340930939, 0.8630799502134323, 0.9812562689185143, 0.8500409945845604, 0.8872993588447571, 0.9518890380859375, 0.817565992474556, 0.8962246030569077, 1.0050299689173698, 0.8698184341192245, 0.9955201968550682, 0.8864745572209358, 0.9703662171959877, 0.8773444220423698, 0.8867345079779625, 0.8644315078854561, 1.0524616912007332, 1.0471714660525322, 0.8520347326993942, 0.7824022993445396, 0.899863213300705, 0.9117838814854622, 0.8145456835627556, 0.8761632815003395, 0.822271928191185, 0.8423984497785568, 0.7483913525938988, 0.9899580553174019, 0.719050794839859, 0.842836856842041, 0.6690901666879654, 0.8192540481686592, 0.8583021685481071, 0.9398204684257507, 0.7631887793540955, 0.9141232445836067, 0.9777213484048843, 0.8539954386651516, 0.8883587419986725, 0.8066505640745163, 0.8078480996191502, 0.8075320273637772, 0.8223423734307289, 0.7828903570771217, 0.7919520512223244, 0.8614304289221764, 0.8190630748867989, 0.7238729819655418, 0.8871771693229675, 0.8313164636492729, 0.7884401828050613, 0.8792124502360821, 0.958718866109848, 0.7970094569027424, 0.8608635738492012, 0.8098404407501221, 0.9210979864001274, 0.7223182134330273, 0.8484601154923439, 0.9263757094740868, 0.950003694742918, 0.8348700441420078, 0.7622436359524727, 0.7508747540414333, 0.7102858871221542, 0.9042278900742531, 0.772382028400898, 0.9787304699420929, 0.6833177171647549, 0.8540235497057438, 0.7138570323586464, 0.7020178623497486, 0.8765410594642162, 0.8538256585597992, 0.8833242803812027, 0.8219228461384773, 0.7839039750397205, 0.7952510081231594, 0.6536855325102806, 0.8706101104617119, 0.6961483471095562, 0.7683878690004349, 0.9696009904146194, 0.7954438664019108, 0.7606731429696083, 0.6363744623959064, 0.7857766598463058, 0.711447149515152, 0.7290543988347054, 0.8191162198781967, 0.795108325779438, 0.8155902251601219, 0.684990007430315, 0.7052396833896637, 0.7292886152863503, 0.80703005194664, 0.7465468347072601, 0.7876842841506004, 0.6599123850464821, 0.6966917887330055, 0.653862539678812, 0.6642164476215839, 0.7386725172400475, 0.7888849042356014, 0.7474425993859768, 0.5695549510419369, 0.7247434891760349, 0.7030610665678978, 0.7257729098200798, 0.6848102323710918, 0.7138721346855164, 0.817454993724823, 0.7975944131612778, 0.6674898117780685, 0.7054434567689896, 0.7587885744869709, 0.7516531981527805, 0.6823097802698612, 0.6152523867785931, 0.7419688329100609, 0.5874418392777443, 0.7610486075282097, 0.6706042550504208, 0.7194474376738071, 0.6557467691600323, 0.7304140515625477, 0.7258985266089439, 0.711428314447403, 0.6588941775262356, 0.6703114844858646, 0.7233006060123444, 0.639919251203537, 0.6698575168848038, 0.6026790328323841, 0.640886202454567, 0.6752652078866959, 0.7496866509318352, 0.7488212399184704, 0.6532691717147827, 0.6341547630727291, 0.6481029130518436, 0.6348367594182491, 0.7067583575844765, 0.5804365277290344, 0.6727160252630711, 0.6469141021370888, 0.7273334674537182, 0.6701151505112648, 0.6009007915854454, 0.5638241544365883, 0.6520540155470371, 0.6558245494961739, 0.6111919991672039, 0.5187827050685883, 0.6361267305910587, 0.6847889870405197, 0.5407768376171589, 0.5685409344732761, 0.7485521212220192, 0.5974139012396336, 0.6587788499891758, 0.7378576621413231, 0.5843271836638451, 0.5825667977333069, 0.7118164785206318, 0.5230779089033604, 0.6985290721058846, 0.7568556144833565, 0.6141550168395042, 0.5092651136219501, 0.5267220512032509, 0.6629782058298588, 0.6334763206541538, 0.5534511283040047, 0.5305191427469254, 0.6167205683887005, 0.5618909299373627, 0.5972632430493832, 0.5695565193891525, 0.5336479879915714, 0.6011861152946949, 0.5896372832357883, 0.5350294560194016, 0.5718418397009373, 0.5490147024393082, 0.5133906975388527, 0.6318588890135288, 0.539122961461544, 0.5813849754631519, 0.5152388475835323, 0.4632333442568779, 0.6345480158925056, 0.5249708443880081, 0.484426774084568, 0.533256147056818, 0.4472791589796543, 0.4763013906776905, 0.48602286353707314, 0.6925303265452385, 0.5076732560992241, 0.600530244410038, 0.4564790055155754, 0.667223297059536, 0.5987365543842316, 0.42909254506230354, 0.5874784961342812, 0.6154694259166718, 0.6053737178444862, 0.7852300703525543, 0.5127655304968357, 0.4787132367491722, 0.4798729307949543, 0.5718159303069115, 0.6152176409959793, 0.6426425278186798, 0.5388281308114529, 0.5774592887610197, 0.6159992516040802, 0.4334101565182209, 0.545670822262764, 0.5395996421575546, 0.43953343108296394, 0.5438551604747772, 0.4187212474644184, 0.5877718292176723, 0.47373973205685616, 0.6454063542187214, 0.5666967071592808, 0.6018067598342896, 0.6273455955088139, 0.58688959851861, 0.5890347734093666, 0.47373466566205025, 0.45447761937975883, 0.5240114964544773, 0.47421785816550255, 0.5149341858923435, 0.5145731773227453, 0.4286866392940283, 0.5144210159778595, 0.5273164883255959, 0.554045245051384, 0.45046695694327354, 0.4659602902829647, 0.5015699937939644, 0.5564818866550922, 0.48412515223026276, 0.4984082616865635, 0.44210636615753174, 0.580976203083992, 0.47407860681414604, 0.4463565871119499, 0.5505729503929615, 0.5157480016350746, 0.4106235485523939, 0.7883365042507648, 0.4764837436378002, 0.4889208506792784, 0.5389044545590878, 0.4730101451277733, 0.557109110057354, 0.5441131889820099, 0.49467410147190094, 0.5130657367408276, 0.5159389711916447, 0.4772080332040787, 0.4540075361728668, 0.5582466553896666, 0.4865749441087246, 0.5580239705741405, 0.5817492231726646, 0.4803249314427376, 0.39883916452527046, 0.47060098499059677, 0.4321296326816082, 0.4790187031030655, 0.38294317200779915, 0.4609317295253277, 0.37732572853565216, 0.4164629280567169, 0.47517436370253563, 0.4504173509776592, 0.41863859072327614, 0.45189379155635834, 0.47776490822434425, 0.3609735555946827, 0.550354391336441, 0.3908670525997877, 0.5960665419697762, 0.3803097791969776, 0.5490386299788952, 0.4074864313006401, 0.3750888090580702, 0.3747303318232298, 0.5319137386977673, 0.32816884852945805, 0.40004071220755577, 0.4819964785128832, 0.34843391366302967, 0.3921263515949249, 0.2740109860897064, 0.40423290990293026, 0.44183551520109177, 0.3250882513821125, 0.5369864888489246, 0.35167569294571877, 0.5025353878736496, 0.4249256048351526, 0.3616291806101799, 0.4472092241048813, 0.41043078526854515, 0.355146499350667, 0.4099423326551914, 0.4098476767539978, 0.4910994954407215, 0.42718709632754326, 0.3952529653906822, 0.34517147578299046, 0.4505896046757698, 0.37559322640299797, 0.39783971197903156, 0.4087483771145344, 0.41268314234912395, 0.42924914695322514, 0.42884546518325806, 0.5290679521858692, 0.34893161430954933, 0.3685067053884268, 0.5414165146648884, 0.39093292504549026, 0.3179291822016239, 0.3442990202456713, 0.33584099262952805, 0.3836049549281597, 0.3143754471093416, 0.4078214969485998, 0.4025356788188219, 0.4287611488252878, 0.3990090824663639, 0.3319474756717682, 0.4468804970383644, 0.3874210733920336, 0.3786114100366831, 0.29810318909585476, 0.44214133359491825, 0.3604597393423319, 0.4883322212845087, 0.33309541270136833, 0.4551389254629612, 0.3017432503402233, 0.45399020053446293, 0.5051603987812996, 0.43226176127791405, 0.3624640814960003, 0.3570117708295584, 0.3733513616025448, 0.4535994529724121, 0.5202502626925707, 0.3536442592740059, 0.40427615866065025, 0.3291198369115591, 0.38144493848085403, 0.4372357912361622, 0.3566617798060179, 0.35901820100843906, 0.4387468695640564, 0.42314667254686356, 0.34205471351742744, 0.44646889716386795, 0.38096277974545956, 0.3498020227998495, 0.4609406031668186, 0.26328837871551514, 0.3787465263158083, 0.38988230377435684, 0.36244175024330616, 0.3392009623348713, 0.3071360159665346, 0.39407413080334663, 0.32230797968804836, 0.32488891668617725, 0.42585858702659607, 0.331064198166132, 0.3985544890165329, 0.35064607486128807, 0.40771338529884815, 0.4362723957747221, 0.3371113110333681, 0.4371528681367636, 0.3627698887139559, 0.30254485830664635, 0.37992764450609684, 0.38538732565939426, 0.27419454231858253, 0.29885912872850895, 0.29550181329250336, 0.3771797176450491, 0.3183757420629263, 0.2633150853216648, 0.3594104088842869, 0.3496088143438101, 0.30887406319379807, 0.313388304784894, 0.3624289147555828, 0.3106038700789213, 0.3785692695528269, 0.41250087693333626, 0.39135270193219185, 0.47024791315197945, 0.3077951706945896, 0.4536698218435049, 0.2679633926600218, 0.30122679844498634, 0.3356283586472273, 0.3619418330490589, 0.38517096266150475, 0.2935399357229471, 0.37779308296740055, 0.33831432461738586, 0.3420299533754587, 0.30514038540422916, 0.2841782607138157, 0.3351996559649706, 0.37874136306345463, 0.34840347804129124, 0.295148516073823, 0.33622779697179794, 0.27630795910954475, 0.3465962465852499, 0.3125620521605015, 0.5192483775317669, 0.23585981875658035, 0.34897854551672935, 0.3129640184342861, 0.41732540633529425, 0.37461310625076294, 0.29539234191179276, 0.331904424354434, 0.2566465921700001, 0.3612253274768591, 0.3623577691614628, 0.2472712118178606, 0.4160102568566799, 0.2892369795590639, 0.32622900791466236, 0.41684211790561676, 0.2561379261314869, 0.3792133256793022, 0.2591555919498205, 0.3476925194263458, 0.3101852461695671, 0.28100290335714817, 0.24629667401313782, 0.3922795206308365, 0.27584339305758476, 0.3452586214989424, 0.2544866260141134, 0.27095168456435204, 0.36753277108073235, 0.25657614693045616, 0.37630385998636484, 0.3136639427393675, 0.2696333434432745, 0.34374078549444675, 0.2423944566398859, 0.32739667780697346, 0.32902941666543484, 0.24040089175105095, 0.2620258051902056, 0.21244757995009422, 0.18949334137141705, 0.26175706833601, 0.3863563183695078, 0.2806169241666794, 0.2955304402858019, 0.2586579183116555, 0.3352459501475096, 0.32396637834608555, 0.27855981327593327, 0.2804501075297594, 0.3357185386121273, 0.26623717695474625, 0.3424595668911934, 0.30147859267890453, 0.2744593657553196, 0.22492914088070393, 0.23931961227208376, 0.2146723922342062, 0.38141091354191303, 0.2627644371241331, 0.2834636587649584, 0.2808333355933428, 0.3245625365525484, 0.21030325256288052, 0.27081472612917423, 0.3495597876608372, 0.31880675349384546, 0.25148122012615204, 0.2621099716052413, 0.336503928527236, 0.2818808238953352, 0.3109710942953825, 0.2669419441372156, 0.3574796970933676, 0.27527797035872936, 0.19606325402855873, 0.33192371018230915, 0.3530075866729021, 0.21096396818757057, 0.3278790460899472, 0.22460922226309776, 0.24033096060156822, 0.2924545966088772, 0.26941134221851826, 0.2461726013571024, 0.2717975499108434, 0.26640111580491066, 0.30491637252271175, 0.28334940131753683, 0.27866372652351856, 0.30939390882849693, 0.2724864957854152, 0.23311538342386484, 0.32950498163700104, 0.25695581547915936, 0.36645625345408916, 0.23281905986368656, 0.18356757797300816, 0.3311203848570585, 0.23769329767674208, 0.3166381549090147, 0.2995806820690632, 0.29032797180116177, 0.1976991705596447, 0.3076410470530391, 0.23728379048407078, 0.22397324908524752, 0.2717601843178272, 0.24651584774255753, 0.218079948797822, 0.23912490531802177, 0.27925547026097775, 0.19324381463229656, 0.21376958303153515, 0.25610336661338806, 0.2449609860777855, 0.21094714850187302, 0.2497727768495679, 0.19362040050327778, 0.3117138650268316, 0.24424660485237837, 0.34353786148130894, 0.2650612276047468, 0.19912491273134947, 0.3002261817455292, 0.27786614187061787, 0.29868085496127605, 0.3406573086977005, 0.23953099455684423, 0.23471915815025568, 0.22971067391335964, 0.2523669768124819, 0.24226050078868866, 0.22909153811633587, 0.23840558901429176, 0.27173235826194286, 0.24175042379647493, 0.32581524550914764, 0.23029949888586998, 0.31688171811401844, 0.20754047390073538, 0.22383768297731876, 0.2271738238632679, 0.29524690099060535, 0.2679588794708252, 0.28034826181828976, 0.24251134786754847, 0.2951580509543419, 0.20683781430125237, 0.21373349241912365, 0.16058302484452724, 0.2747149523347616, 0.21643309574574232, 0.21270966716110706, 0.23107499349862337, 0.31812434177845716, 0.20389128848910332, 0.27876269072294235, 0.33432207722216845, 0.2235050229355693, 0.23257502540946007, 0.20397264696657658, 0.18768707569688559, 0.20506846066564322, 0.24087853822857141, 0.2152798492461443, 0.20570152439177036, 0.303055714815855, 0.2683182470500469, 0.32761078514158726, 0.17594860773533583, 0.2124567711725831, 0.2943982593715191, 0.24800152704119682, 0.24715036898851395, 0.17351961322128773, 0.2143412558361888, 0.2953307293355465, 0.18465332686901093, 0.22176744602620602, 0.19920417200773954, 0.16190624982118607, 0.2656880412250757, 0.21846376918256283, 0.15688989125192165, 0.2089139660820365, 0.19886876177042723, 0.21413975954055786, 0.18966774828732014, 0.2637917436659336, 0.19158015213906765, 0.21085229702293873, 0.31015480775386095, 0.26967317052185535, 0.241744845174253, 0.22009945195168257, 0.1445802105590701, 0.2691789409145713, 0.22764472663402557, 0.22592899296432734, 0.13186838664114475, 0.14391414355486631, 0.17463022470474243, 0.17308455798774958, 0.3118295893073082, 0.1841737236827612, 0.2045324370265007, 0.13774806633591652, 0.2563496623188257, 0.18096559215337038, 0.18718648608773947, 0.16713913716375828, 0.1921495832502842, 0.21153031941503286, 0.16109741758555174, 0.2950601880438626, 0.24544633459299803, 0.2053263084962964, 0.3157817590981722, 0.24165480211377144, 0.21327843982726336, 0.19000977370887995, 0.2303895615041256, 0.15998652670532465, 0.23596514016389847, 0.194579198025167, 0.19932351261377335, 0.20007285475730896, 0.16445507667958736, 0.23086488991975784, 0.161231460981071, 0.2334051290526986, 0.2724085561931133, 0.2432806622236967, 0.17694840673357248, 0.28494652546942234, 0.1575956605374813, 0.2692051138728857, 0.17248323559761047, 0.2962628612294793, 0.2526730438694358, 0.21521438378840685, 0.16972641926258802, 0.15075407270342112, 0.26126884762197733, 0.1817370941862464, 0.2346579721197486, 0.16231029853224754, 0.2219141898676753, 0.2319217137992382, 0.1543560540303588, 0.2447512522339821, 0.21601359732449055, 0.15276906173676252, 0.1522657135501504, 0.18734951131045818, 0.19556180573999882, 0.22091563791036606, 0.14082259126007557, 0.2811478963121772, 0.14551733061671257, 0.23522278852760792, 0.3064004057087004, 0.15156082343310118, 0.23983637522906065, 0.1806510053575039, 0.23361283168196678, 0.14508092496544123, 0.17725927382707596, 0.18119185511022806, 0.21640378795564175, 0.2045394331216812, 0.14883764553815126, 0.15325975976884365, 0.20653920993208885, 0.14503802452236414, 0.1560771083459258, 0.16858192160725594, 0.18520362116396427, 0.2224221145734191, 0.19841525610536337, 0.19107069075107574, 0.1462620459496975, 0.19317145366221666, 0.1753430115059018, 0.14182135742157698, 0.17320586275309324, 0.21220603957772255, 0.13793467544019222, 0.1993019706569612, 0.19889439921826124, 0.16976585146039724, 0.2622493915259838, 0.12853433564305305, 0.2554188733920455, 0.13507454376667738, 0.20257796440273523, 0.22346610855311155, 0.17552438843995333, 0.25322883762419224, 0.16562476381659508, 0.17703446187078953, 0.14046394219622016, 0.20424659084528685, 0.14415062218904495, 0.11003229627385736, 0.17842554114758968, 0.182915517129004, 0.24494743160903454, 0.14050066331401467, 0.16170512605458498, 0.28884131368249655, 0.14032712997868657, 0.1495514214038849, 0.18321269191801548, 0.1682196594774723, 0.2271101474761963, 0.29053959995508194, 0.22765217628329992, 0.16434500366449356, 0.21379428077489138, 0.1787145035341382, 0.1629427233710885, 0.17569746915251017, 0.17705942504107952, 0.16968480218201876, 0.20118559198454022, 0.13099635671824217, 0.2327681938186288, 0.19823661353439093, 0.15853058826178312, 0.18527989089488983, 0.17238478548824787, 0.18098580837249756, 0.17823267029598355, 0.18768930714577436, 0.17813807632774115, 0.15267739724367857, 0.1500853570178151, 0.19305119290947914, 0.2595939617604017, 0.22287175711244345, 0.1482454352080822, 0.1506286202929914, 0.23721319623291492, 0.14839634485542774, 0.19320244807749987, 0.12208925187587738, 0.1188717046752572, 0.1477219918742776, 0.13231411250308156, 0.21048546768724918, 0.11864038277417421, 0.14499254990369081, 0.2606329647824168, 0.12485404778271914, 0.09980922751128674, 0.14357956033200026, 0.18644130695611238, 0.1842710431665182, 0.16212251409888268, 0.1580122597515583, 0.13097347086295485, 0.13302835589274764, 0.14574947766959667, 0.1546881259419024, 0.17933677975088358, 0.10104626975953579, 0.17103199008852243, 0.1483780713751912, 0.14552859775722027, 0.19122371543198824, 0.12288633268326521, 0.10356262233108282, 0.1678215954452753, 0.11813260987401009, 0.1246391637250781, 0.1384459501132369, 0.20922434469684958, 0.21087625809013844, 0.1325465887784958, 0.17296011233702302, 0.17169525939971209 ], "initial_loss": 8.261292934417725, "final_loss": 0.17169525939971209, "loss_delta": 8.089597675018013, "final_validation_loss": 0.22703046803673108, "final_validation_perplexity": 1.254868100725223, "parameter_counts": { "total": 9106112512, "trainable": 751710208 }, "optimizer_name": "adam8bit", "adapter_enabled": true, "surgery_plan": { "use_mla": true, "use_qk_norm": true, "use_post_norm": true, "use_moe_layers": true, "use_recurrent_layers": true, "use_mtp_head": true, "qk_norm_layers": [], "qk_norm_eps": 1e-05, "mla_layers": [], "moe_layers": [], "recurrent_layers": [] }, "surgery_inspection": { "total_layers": 32, "sliding_mla_layers": 16, "global_moe_layers": 8, "recurrent_layers": 8, "mla_modules": 24, "moe_modules": 8, "recurrent_modules": 8, "post_norm_layers": 32, "has_mtp_head": true, "schedule": { "sliding_mla_layers": [ 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 ], "global_moe_layers": [ 3, 7, 11, 15, 19, 23, 27, 31 ], "recurrent_layers": [ 1, 5, 9, 13, 17, 21, 25, 29 ] } } }